| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9841269841269841, | |
| "eval_steps": 500, | |
| "global_step": 31, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1e-06, | |
| "loss": 4.7267, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.972609476841365e-07, | |
| "loss": 4.8062, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.890738003669027e-07, | |
| "loss": 4.8224, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 9.755282581475767e-07, | |
| "loss": 4.67, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.567727288213004e-07, | |
| "loss": 4.5396, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.330127018922193e-07, | |
| "loss": 4.5491, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.045084971874737e-07, | |
| "loss": 4.1372, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 8.71572412738697e-07, | |
| "loss": 4.0975, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 8.34565303179429e-07, | |
| "loss": 3.9547, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 7.938926261462365e-07, | |
| "loss": 3.9552, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 7.5e-07, | |
| "loss": 3.1564, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 7.033683215379002e-07, | |
| "loss": 2.9562, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 6.545084971874736e-07, | |
| "loss": 2.8965, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 6.039558454088795e-07, | |
| "loss": 2.8619, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5.522642316338268e-07, | |
| "loss": 2.7833, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 5e-07, | |
| "loss": 2.8085, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.477357683661733e-07, | |
| "loss": 2.6707, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 3.960441545911204e-07, | |
| "loss": 2.5077, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.454915028125263e-07, | |
| "loss": 2.4973, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 2.9663167846209996e-07, | |
| "loss": 2.4912, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2.500000000000001e-07, | |
| "loss": 2.4112, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.0610737385376348e-07, | |
| "loss": 2.4614, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.6543469682057104e-07, | |
| "loss": 2.3531, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.284275872613028e-07, | |
| "loss": 2.4098, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 9.549150281252632e-08, | |
| "loss": 2.3701, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 6.698729810778064e-08, | |
| "loss": 2.3197, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 4.322727117869951e-08, | |
| "loss": 2.1932, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 2.4471741852423233e-08, | |
| "loss": 2.2083, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.0926199633097154e-08, | |
| "loss": 2.0796, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 2.739052315863355e-09, | |
| "loss": 2.1377, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.0, | |
| "loss": 2.1141, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "step": 31, | |
| "total_flos": 7923264405504.0, | |
| "train_loss": 3.127300493178829, | |
| "train_runtime": 487.5498, | |
| "train_samples_per_second": 8.212, | |
| "train_steps_per_second": 0.064 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 31, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 7975, | |
| "total_flos": 7923264405504.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |